Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1927 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9836. Min Act: -0.0000

Data Index: 573190 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1436110 (The Pile)

Max Activating Token Index: 530

Text #2

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.6105. Min Act: -0.0000

Data Index: 365354 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1732257 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1445645 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.2509. Min Act: -0.0000

Data Index: 402294 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1794024 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1444464 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.1681. Min Act: -0.0000

Data Index: 388085 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.0932. Min Act: -0.0000

Data Index: 211126 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1612422 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 1.9836. Min Range: -1.9836

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1418204 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.0142. Min Act: -0.0000

Data Index: 203060 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 1.9836. Min Range: -1.9836

Max Act: 0.9797. Min Act: -0.0000

Data Index: 55812 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.0009. Min Act: -0.0000

Data Index: 938207 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1904044 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.9836. Min Range: -1.9836

Max Act: 0.9935. Min Act: 0.0000

Data Index: 1906935 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 1.9836. Min Range: -1.9836

Max Act: 0.8941. Min Act: -0.0000

Data Index: 830964 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 1.9836. Min Range: -1.9836

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1714119 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 1.9836. Min Range: -1.9836

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1165354 (The Pile)

Max Activating Token Index: 242